City-Scale Holographic Traffic Flow Data based on Vehicular Trajectory Resampling

Despite abundant accessible traffic data, researches on traffic flow estimation and optimization still face the dilemma of detailedness and integrity in the measurement. A dataset of city-scale vehicular continuous trajectories featuring the finest resolution and integrity, as known as the holographic traffic data, would be a breakthrough, for it could reproduce every detail of the traffic flow evolution and reveal the personal mobility pattern within the city. Due to the high coverage of Automatic Vehicle Identification (AVI) devices in Xuancheng city, we constructed one-month continuous trajectories of daily 80,000 vehicles in the city with accurate intersection passing time and no travel path estimation bias. With such holographic traffic data, it is possible to reproduce every detail of the traffic flow evolution.

This collection is a city-scale traffic flow dataset of Xuancheng City, China. It contains 3 types of data:

1. One-month-long resampled traffic flow dataset, including stationary loop data and dynamic floating car data (FCD).

- loop_data.csv: The location of the loops are set to the middle of the road segments, providing speed and flow data of 5-minute intervals.

- fcd_data.csv: The FCD gives the trajectories of the 500 commercial vehicles every 10 seconds.

- road_network_segment_level.csv: The road segment description.

2. One-month long encrypted trajectories and command-line tool. With this command-line tool, users can modify the locations and other settings of loops and floating cars, and get customized results, meanwhile, the personal trajectories would not be abused.

- fullTraj.zip: The one-month holographic trajectories of all vehicles in Xuancheng

- command_line_tool.csv: The command-line tool for virtual traffic flow detection, packed with the user instruction and one-day trajectories for demonstration. The software can run on Windows, Linux, and macOS systems.

3. One-hour original vehicle license plate recognition (LPR) dataset. This is for reproducing the trajectory reconstruction method.

- lpr.csv: The original LPR data from 8:00 to 9:00 on the morning peak of a workday.

- signal.csv: The traffic signal data from the same time as LPR data. It is the supplemental input data for the reconstruction method.

- road_network_stream_level.csv: The road network of the traffic stream level for the reconstruction method.